paper-with-me

홈 › Papers

Deep Generative Model for Joint Alignment and Word Representation

2018-02-16 · NAACL 2018 6 · Miguel Rios, Wilker Aziz, Khalil Sima'an

This work exploits translation data as a source of semantically relevant learning signal for models of word representation. In particular, we exploit equivalence through translation as a form of distributed context and jointly learn how to embed and align with a deep generative model. Our EmbedAlign model embeds words in their complete observed context and learns by marginalisation of latent lexical alignments. Besides, it embeds words as posterior probability densities, rather than point estimates, which allows us to compare words in context using a measure of overlap between distributions (e.g. KL divergence). We investigate our model's performance on a range of lexical semantics tasks achieving competitive results on several standard benchmarks including natural language inference, paraphrasing, and text similarity.

📄 PDF Abstract BibTeX arXiv:1802.05883

Code (1)

uva-slpl/embedalign 공식 구현 tf

Tasks

Natural Language Inferencetext similarityTranslation

Similar Papers 제목 키워드 기반

Consistent Alignment of Word Embedding Models

2017-02-24 · Cem Safak Sahin, Rajmonda S. Caceres, Brandon Oselio, William M. Campbell

Word embedding models offer continuous vector representations that can capture rich contextual semantics based on their word co-occurrence patterns. While these word vectors can provide very effective features used in ma…

Clustering

Improving Word Alignment of Rare Words with Word Embeddings

2016-12-01 · COLING 2016 12 · Masoud Jalili Sabet, Heshaam Faili, Gholamreza Haffari

We address the problem of inducing word alignment for language pairs by developing an unsupervised model with the capability of getting applied to other generative alignment models. We approach the task by: i)proposing a…

Machine TranslationSentenceWord AlignmentWord Embeddings

Large-scale Word Alignment Using Soft Dependency Cohesion Constraints

2013-01-01 · TACL 2013 1 · Zhiguo Wang, Cheng-qing Zong

Dependency cohesion refers to the observation that phrases dominated by disjoint dependency subtrees in the source language generally do not overlap in the target language. It has been verified to be a useful constraint …

Machine TranslationTranslationWord Alignment

Neural Text Classification by Jointly Learning to Cluster and Align

2020-11-24 · Yekun Chai, Haidong Zhang, Shuo Jin

Distributional text clustering delivers semantically informative representations and captures the relevance between each word and semantic clustering centroids. We extend the neural text clustering approach to text class…

ClassificationClusteringGeneral Classificationtext-classification+3

Generative latent neural models for automatic word alignment

2020-09-28 · AMTA 2020 10 · Anh Khoa Ngo Ho, François Yvon

Word alignments identify translational correspondences between words in a parallel sentence pair and are used, for instance, to learn bilingual dictionaries, to train statistical machine translation systems or to perform…

Machine TranslationSentenceText GenerationTranslation+1